[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6CD35JW73TPMCZBF9DTDEE8":3,"skill-same:01M6CD35JW73TPMCZBF9DTDEE8":63},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":27,"linkOnly":28,"markdownContent":29,"markdownBody":30,"frontMatter":31,"refName":37,"commitSha":38,"skillDirectory":39,"forksCount":14,"repositoryHtmlUrl":40,"repositoryHomepageUrl":6,"ownerHtmlUrl":41,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":42,"install":43,"resources":56},"01M6CD35JW73TPMCZBF9DTDEE8","steering-matcher",null,"Match file paths against steering file glob patterns to determine applicable steering guidance. Use when orchestrator needs to inject context-aware guidance based on files being modified.","loriensleafs\u002Fbrain","loriensleafs","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F315385?v=4","01M6CCYZETMCJPTHNS258YRCBC","Peter Kloss","01M6CCYZK25T8516A39S9PCJT7",0,"MIT","https:\u002F\u002Fgithub.com\u002Floriensleafs\u002Fbrain\u002Fblob\u002Fmain\u002Ftemplates\u002Fskills\u002Fsteering-matcher\u002FSKILL.md",[],[19,20,21,22,23,24,25,26],"steering matcher","file","haiku","context","orchestrator","use","files","guidance","2026-11-10 10:12:30",false,"---\nname: steering-matcher\ndescription: Match file paths against steering file glob patterns to determine applicable steering guidance. Use when orchestrator needs to inject context-aware guidance based on files being modified.\nlicense: MIT\nagents: [orchestrator]\nmodel: claude-haiku-4-5\nmetadata:\n  version: 1.0.0\n  timelessness: high\n---\n\n# Steering File Matcher Skill\n\n## Triggers\n\n| Trigger Phrase | Operation |\n|----------------|-----------|\n| `match steering for these files` | get_applicable_steering.ts |\n| `which steering applies to this task` | Pattern match against changed files |\n| `inject steering context` | Return applicable steering sorted by priority |\n\n## Purpose\n\nThis skill helps orchestrator determine which steering files to inject into agent context based on the files being modified.\n\n- Match file paths against glob patterns in steering file front matter\n- Return applicable steering files sorted by priority\n- Enable token-efficient context injection (30%+ savings)\n\n## When to Use\n\nUse this skill when:\n\n- Orchestrator needs to inject context-aware steering based on files being modified\n- You want to scope agent guidance to only relevant files (token optimization)\n- Matching file paths against `applyTo` glob patterns in steering front matter\n\nUse manual file reading instead when:\n\n- You already know which steering file applies\n- The task affects a single known steering domain\n\n## Quick Usage\n\n### Using get_applicable_steering.ts Script\n\nThe script in `scripts\u002Fget_applicable_steering.ts` handles pattern matching.\n\n```bash\n# Match files against steering patterns\nbun run ${CLAUDE_SKILL_DIR}\u002Fscripts\u002Fget_applicable_steering.ts \\\n    --files \"src\u002Fclaude\u002Fanalyst.md\" \".agents\u002Fsecurity\u002FTM-001-auth-flow.md\" \\\n    --steering-path \".agents\u002Fsteering\"\n\n# Output: JSON array of objects with name, path, apply_to, priority\n```\n\n## Process\n\nThis skill integrates with the orchestrator workflow:\n\n1. **Task Analysis**: Orchestrator identifies files affected by task\n2. **Pattern Matching**: Use this skill to find applicable steering\n3. **Context Injection**: Include matched steering in agent prompt\n4. **Token Optimization**: Only inject relevant guidance\n\n### Standard Orchestrator Workflow\n\n```bash\n# 1. Identify files from task\n# 2. Get applicable steering\nbun run ${CLAUDE_SKILL_DIR}\u002Fscripts\u002Fget_applicable_steering.ts \\\n    --files \"src\u002Fclaude\u002Fsecurity.md\" \".agents\u002Fsecurity\u002FSR-001-oauth-review.md\"\n\n# 3. Inject into agent context\n# Output: JSON with name, path, apply_to, priority sorted by priority descending\n```\n\n## Implementation\n\nSee `scripts\u002Fget_applicable_steering.ts` for the TypeScript implementation.\n\n## Anti-Patterns\n\n| Avoid | Why | Instead |\n|-------|-----|---------|\n| Hardcoding steering file paths | Bypasses pattern matching, breaks on restructuring | Use get_applicable_steering.ts |\n| Injecting all steering files | Token bloat, irrelevant context | Match against changed files only |\n| Ignoring priority ordering | Lower-priority guidance may contradict higher | Process results in priority order |\n\n## Verification\n\nAfter execution:\n\n- [ ] Returned steering files match the `applyTo` patterns for the given files\n- [ ] Results are sorted by priority (highest first)\n- [ ] No duplicate steering entries in output\n\n## Scripts\n\n### get_applicable_steering.ts\n\nMatches file paths against steering glob patterns and returns applicable guidance.\n\n```bash\nbun run ${CLAUDE_SKILL_DIR}\u002Fscripts\u002Fget_applicable_steering.ts --files \u003Cfile1> [\u003Cfile2> ...]\n```\n\n## Related\n\n- [Steering System README](..\u002F..\u002F..\u002F.agents\u002Fsteering\u002FREADME.md)\n- [Enhancement Project Plan](..\u002F..\u002F..\u002F.agents\u002Fplanning\u002Fenhancement-PROJECT-PLAN.md)\n- [Orchestrator Agent](..\u002F..\u002F..\u002Fsrc\u002Fclaude\u002Forchestrator.md)\n","# Steering File Matcher Skill\n\n## Triggers\n\n| Trigger Phrase | Operation |\n|----------------|-----------|\n| `match steering for these files` | get_applicable_steering.ts |\n| `which steering applies to this task` | Pattern match against changed files |\n| `inject steering context` | Return applicable steering sorted by priority |\n\n## Purpose\n\nThis skill helps orchestrator determine which steering files to inject into agent context based on the files being modified.\n\n- Match file paths against glob patterns in steering file front matter\n- Return applicable steering files sorted by priority\n- Enable token-efficient context injection (30%+ savings)\n\n## When to Use\n\nUse this skill when:\n\n- Orchestrator needs to inject context-aware steering based on files being modified\n- You want to scope agent guidance to only relevant files (token optimization)\n- Matching file paths against `applyTo` glob patterns in steering front matter\n\nUse manual file reading instead when:\n\n- You already know which steering file applies\n- The task affects a single known steering domain\n\n## Quick Usage\n\n### Using get_applicable_steering.ts Script\n\nThe script in `scripts\u002Fget_applicable_steering.ts` handles pattern matching.\n\n```bash\n# Match files against steering patterns\nbun run ${CLAUDE_SKILL_DIR}\u002Fscripts\u002Fget_applicable_steering.ts \\\n    --files \"src\u002Fclaude\u002Fanalyst.md\" \".agents\u002Fsecurity\u002FTM-001-auth-flow.md\" \\\n    --steering-path \".agents\u002Fsteering\"\n\n# Output: JSON array of objects with name, path, apply_to, priority\n```\n\n## Process\n\nThis skill integrates with the orchestrator workflow:\n\n1. **Task Analysis**: Orchestrator identifies files affected by task\n2. **Pattern Matching**: Use this skill to find applicable steering\n3. **Context Injection**: Include matched steering in agent prompt\n4. **Token Optimization**: Only inject relevant guidance\n\n### Standard Orchestrator Workflow\n\n```bash\n# 1. Identify files from task\n# 2. Get applicable steering\nbun run ${CLAUDE_SKILL_DIR}\u002Fscripts\u002Fget_applicable_steering.ts \\\n    --files \"src\u002Fclaude\u002Fsecurity.md\" \".agents\u002Fsecurity\u002FSR-001-oauth-review.md\"\n\n# 3. Inject into agent context\n# Output: JSON with name, path, apply_to, priority sorted by priority descending\n```\n\n## Implementation\n\nSee `scripts\u002Fget_applicable_steering.ts` for the TypeScript implementation.\n\n## Anti-Patterns\n\n| Avoid | Why | Instead |\n|-------|-----|---------|\n| Hardcoding steering file paths | Bypasses pattern matching, breaks on restructuring | Use get_applicable_steering.ts |\n| Injecting all steering files | Token bloat, irrelevant context | Match against changed files only |\n| Ignoring priority ordering | Lower-priority guidance may contradict higher | Process results in priority order |\n\n## Verification\n\nAfter execution:\n\n- [ ] Returned steering files match the `applyTo` patterns for the given files\n- [ ] Results are sorted by priority (highest first)\n- [ ] No duplicate steering entries in output\n\n## Scripts\n\n### get_applicable_steering.ts\n\nMatches file paths against steering glob patterns and returns applicable guidance.\n\n```bash\nbun run ${CLAUDE_SKILL_DIR}\u002Fscripts\u002Fget_applicable_steering.ts --files \u003Cfile1> [\u003Cfile2> ...]\n```\n\n## Related\n\n- [Steering System README](..\u002F..\u002F..\u002F.agents\u002Fsteering\u002FREADME.md)\n- [Enhancement Project Plan](..\u002F..\u002F..\u002F.agents\u002Fplanning\u002Fenhancement-PROJECT-PLAN.md)\n- [Orchestrator Agent](..\u002F..\u002F..\u002Fsrc\u002Fclaude\u002Forchestrator.md)\n",{"name":5,"model":32,"agents":33,"license":15,"metadata":34,"description":7},"claude-haiku-4-5",[23],{"version":35,"timelessness":36},"1.0.0","high","main","2bd10cb7ca989f88dbf338b57957763718eda59b","templates\u002Fskills\u002Fsteering-matcher","https:\u002F\u002Fgithub.com\u002Floriensleafs\u002Fbrain","https:\u002F\u002Fgithub.com\u002Floriensleafs","2026-03-11 23:51:59",{"source":8,"skillName":5,"commands":44,"prompt":54,"zipAvailable":55},[45,48,51],{"tool":46,"command":47},"npx","npx skills add loriensleafs\u002Fbrain --skill steering-matcher",{"tool":49,"command":50},"bunx","bunx skills add loriensleafs\u002Fbrain --skill steering-matcher",{"tool":52,"command":53},"pnpm","pnpm dlx skills add loriensleafs\u002Fbrain --skill steering-matcher","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Floriensleafs\u002Fbrain\u002Fblob\u002Fmain\u002Ftemplates\u002Fskills\u002Fsteering-matcher\u002FSKILL.md",true,[57],{"path":58,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":61,"sourceHtmlUrl":62},"scripts\u002Fget_applicable_steering.ts","SCRIPT","脚本",4914,"https:\u002F\u002Fgithub.com\u002Floriensleafs\u002Fbrain\u002Fblob\u002Fmain\u002Ftemplates\u002Fskills\u002Fsteering-matcher\u002Fscripts\u002Fget_applicable_steering.ts",[64,80,95,118,138,162],{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":27},"01M6CD3KHDHPR633RVP95G4XWN","validation-authority","Treat upstream validators as authoritative. Align local config to them. Use when validation fails unexpectedly, before modifying validator behavior, or when tempted to change upstream tool code.","https:\u002F\u002Fgithub.com\u002Floriensleafs\u002Fbrain\u002Fblob\u002Fmain\u002Ftemplates\u002Fskills\u002Fvalidation-authority\u002FSKILL.md",[],[71,72,73,74,24,75,76,77,78,79],"validation authority","validation","behavior","implementer","change","code","config","architect","tool",{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":27},"01M6CD3H29Q8FWN9YETT8YVQTS","using-brain-memory","Guidance for using Brain semantic memory effectively. Applies Zettelkasten atomic note principles with observations and relations. Use when deciding whether to query or create notes, structuring note content, or understanding the semantic knowledge graph.","https:\u002F\u002Fgithub.com\u002Floriensleafs\u002Fbrain\u002Fblob\u002Fmain\u002Ftemplates\u002Fskills\u002Fusing-forgetful-memory\u002FSKILL.md",[],[87,88,89,26,24,22,90,91,92,93,94],"memory","using brain memory","content","knowledge","knowledge graph","graph","create","notes",{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"publishedAt":27},"01M6CD3E2KTTMNSWXRJAAZA7D1","threat-modeling","Structured security analysis using OWASP Four-Question Framework and STRIDE methodology. Generates threat matrices with risk ratings, mitigations, and prioritization. Use for attack surface analysis, security architecture review, or when asking what can go wrong.","https:\u002F\u002Fgithub.com\u002Floriensleafs\u002Fbrain\u002Fblob\u002Fmain\u002Ftemplates\u002Fskills\u002Fthreat-modeling\u002FSKILL.md",[],[102,103,104,105,106,107,108,109,110,111,112,113,114,115,24,116,78,117],"threat modeling","threat","analysis","stride","risk","owasp","methodology","framework","security analysis","architecture review","architecture","security","go","review","question","prioritization",{"skillNo":119,"name":120,"nameZh":6,"description":121,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":122,"categories":123,"keywords":129,"publishedAt":27},"01M6CD3BC6G0Q2MDNW6X51XHBQ","taste-lints","Custom lints with agent-readable remediation instructions. Enforces taste invariants (file size, naming conventions, structured logging, complexity) and surfaces errors that agents can act on directly. Use when writing or reviewing code to catch style violations early.","https:\u002F\u002Fgithub.com\u002Floriensleafs\u002Fbrain\u002Fblob\u002Fmain\u002Ftemplates\u002Fskills\u002Ftaste-lints\u002FSKILL.md",[124],{"categoryNo":125,"categoryName":126,"taxonomyType":127,"taxonomyTypeDesc":128},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[130,131,132,133,24,134,20,135,136,76,137,74],"taste lints","remediation","surfaces","complexity","instructions","logging","qa","writing",{"skillNo":139,"name":140,"nameZh":6,"description":141,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":142,"categories":143,"keywords":144,"publishedAt":27},"01M6CD37Z7VD22BH42TG0GM66V","style-enforcement","Validate code against style rules from .editorconfig, StyleCop.json, and Directory.Build.props. Detects line ending violations, naming convention issues, indentation problems, and charset mismatches across C#, Python, TypeScript, and JavaScript. Produces JSON reports for pre-commit hooks and CI pipelines.","https:\u002F\u002Fgithub.com\u002Floriensleafs\u002Fbrain\u002Fblob\u002Fmain\u002Ftemplates\u002Fskills\u002Fstyle-enforcement\u002FSKILL.md",[],[145,146,147,148,149,150,74,151,152,153,154,155,156,157,158,136,159,76,160,161],"style enforcement","enforcement","python","typescript","directory","javascript","reports","pipelines","hooks","Rules","json","pre-commit","editorconfig","ci","issues","validate","commit",{"skillNo":163,"name":164,"nameZh":6,"description":165,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":166,"categories":167,"keywords":169,"publishedAt":27},"01M6CD32KG07KWP69SY6F4471S","slashcommandcreator","Autonomous meta-skill for creating high-quality custom slash commands using 5-phase workflow with multi-agent validation and quality gates. Use when user requests new slash command, reusable prompt automation, or wants to convert repetitive workflows into documented commands.","https:\u002F\u002Fgithub.com\u002Floriensleafs\u002Fbrain\u002Fblob\u002Fmain\u002Ftemplates\u002Fskills\u002Fslashcommandcreator\u002FSKILL.md",[168],{"categoryNo":125,"categoryName":126,"taxonomyType":127,"taxonomyTypeDesc":128},[164,170,171,24,74,172,173,174,175,176,177,178,78,179,72,180,181,182,183,113],"quality","reusable","autonomous","user","command","prompt","multi-agent","convert","critic","Meta","quality gates","workflows","automation","workflow"]